Does NQ rebound after a large overnight drop?

One pre-registered study found it did in the first half-hour after the open in 18 out-of-sample trades (about +51 points net, t = 2.49), but with a small sample, nine candidate rules and results concentrated on stress days; the author calls it promising but not proven.

Pre-registered study: NQ rebound after a big overnight drop

Open GitHub research project (author: talalmalikllc-debug), rule frozen 14 October 2026

AA — the trader’s own published text (rule document, own site) was read.

A narrow intraday rule on Nasdaq-100 futures (NQ), 25 minutes long. A rare thing: a rule picked from nine pre-registered candidates on training data only, then tested on validation and test periods with a cost model, a robustness section and a list of the author’s own limitations. The verdict is “promising but not proven”, on 18 out-of-sample trades.

A published rule is a hypothesis, not evidence of profit. We do not know how often these rules won, and traders who publish their methods are the ones who survived.

Sources

nq-post-open-rebound: pre-registered quant study (GitHub README) — open repository, 2026
The README was read. The raw data are not published (licensing), so none of the numbers could be re-computed.

Rules

Filter

FilterOvernight return = 09:30 open ÷ previous 16:00 close − 1; its size z = that return ÷ the standard deviation of the overnight return over the previous 60 days. Condition 1: z ≤ −2.0 (an unusually large drop).
[1]
FilterCondition 2: the price at 09:35 is above the 09:30 open (the first five minutes were up). Skip half-days and the 11 days before quarterly contract expiry; roll windows are excluded.
[1]
FilterThe rule was chosen from 9 candidates (3 drop thresholds × 3 first-five-minute filters) using the training data only, and frozen on 14 October 2026. Data: NQ front month, 1- and 5-minute bars, June 2016 – October 2026, not back-adjusted.
[1]
FilterRobustness (out of sample): median +52.4 points; without the best trade +41.4; without the three best +26.4; bootstrap 95% range of the average +11.6 to +90.7 points.
[1]

Entry

EntryBuy 1 NQ contract at 09:35 New York time.
[1]

Exit

ExitSell at 10:00. No stop and no target.
[1]

Discipline

DisciplineNet of costs (1 tick slippage per side plus $4.50 fees, about 0.7 points round trip; 1 point = $20): train 2016-08…2021 — 38 trades, +7.9 points, t = 1.86; validation 2022–2023 — 8 trades, +49.3, t = 1.54; test 2024 – October 2026 — 10 trades, +52.2, t = 1.87.
[1]
DisciplineAll out-of-sample trades together: 18 trades, +50.9 points net on average, 61% winners, t = 2.49 (p ≈ 0.01). The worst trade lost 120 points (25 January 2022).
[1]
DisciplineLimitations listed by the author: only 18 out-of-sample trades (about 4 a year); the rule was picked from 9 candidates and later periods were looked at more than once; the effect is not monotonic (drops of −2 to −1.5 do not rebound); many trades cluster on stress days where real slippage may be worse; costs are modelled from trade prints, not quotes; no risk management, one contract each.
[1]
DisciplineNext step announced by the author: forward paper trading from 14 October 2026 with no parameter changes, aiming at 20–30 new trades.
[1]

Not confirmed

Often attributed to this trader, but not found in the sources above. Not listed as his or her rules.

According to the README the project began as a replication of Iwanaga & Sakemoto (2026), “Does overnight return predict the first half-hour return for U.S. market indices?” (SSRN 5807282), where for NQ the link was about half as strong as for SPY and mostly in the first five minutes, and a momentum variant showed no effect. We did not open that paper.

Limits of these rules

Eighteen trades are too few to separate a real effect from luck, and the author says so. The result also depends on a handful of stress days (24 February 2022, 5 August 2024, April 2025), which is exactly when fills are worst. Treat it as a hypothesis with a forward test pending, not as a rule to trade.

Other traders

Rules are our paraphrase of the sources; only short quotes are verbatim. This is information, not advice or a promise of profit.